The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill makes network requests to official academic and research databases including NCBI (PubMed/PMC), ClinicalTrials.gov, and Unpaywall. These are well-known, trusted scientific infrastructure services used as intended for the skill's research purpose.
[COMMAND_EXECUTION]: The skill executes Python scripts for data retrieval and processing. The commands are clearly defined and operate on structured research data with no signs of shell injection or dangerous command concatenation.
[DATA_EXPOSURE]: The skill uses an ANTHROPIC_API_KEY and an UNPAYWALL_EMAIL for service access. The skill correctly instructs the user to store these in a .env file, which is a standard security best practice for local development to prevent hardcoding secrets.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (abstracts and research papers) which could theoretically contain instructions intended to influence the LLM review phase. However, the risk is low as the data is handled as research text, and the skill's primary function is academic analysis.

literature-research